93 citations · 229 across the 33 of their papers we have counts for
39 papers
Lipschitz Thinking: Ten Years of Certifiable-by-Design Robust Neural Networks
Fabio Brau, Giorgio Piras, Maura Pintor +1
The Lipschitz property of a deep neural network provides a direct measure of its sensitivity to input perturbations and, when explicitly controlled, offers a principled way to limi…
Adversarial Frontiers: Minimum-Norm Attack Ensembles for Robustness Evaluation
Luca Scionis, Luca Melis, Maura Pintor +5
Adversarial robustness is commonly evaluated with predefined attack ensembles, such as AutoAttack, at a single perturbation budget and on a selective choice of pertur…
Latent-space Attacks for Refusal Evasion in Language Models
Giorgio Piras, Raffaele Mura, Fabio Brau +4
Safety-aligned language models are trained to refuse harmful requests, yet refusal behavior can be suppressed by steering their internal representations. Existing methods do so by…
Label-efficient Training Updates for Malware Detection over Time
Luca Minnei, Cristian Manca, Giorgio Piras +6
Machine Learning (ML)-based detectors are becoming essential to counter the proliferation of malware. However, common ML algorithms are not designed to cope with the dynamic nature…
SAGE-5GC: Security-Aware Guidelines for Evaluating Anomaly Detection in the 5G Core Network
Cristian Manca, Christian Scano, Giorgio Piras +3
Machine learning-based anomaly detection systems are increasingly being adopted in 5G Core networks to monitor complex, high-volume traffic. However, most existing approaches are e…
BlackCATT: Black-box Collusion Aware Traitor Tracing in Federated Learning
Elena Rodríguez-Lois, Fabio Brau, Maura Pintor +2
Federated Learning has been popularized in recent years for applications involving personal or sensitive data, as it allows the collaborative training of machine learning models th…
Out-of-Distribution Detection for Continual Learning: Design Principles and Benchmarking
Srishti Gupta, Riccardo Balia, Daniele Angioni +7
Recent years have witnessed significant progress in the development of machine learning models across a wide range of fields, fueled by increased computational resources, large-sca…
Counterfeit Answers: Adversarial Forgery against OCR-Free Document Visual Question Answering
Marco Pintore, Maura Pintor, Dimosthenis Karatzas +1
Document Visual Question Answering (DocVQA) enables end-to-end reasoning grounded on information present in a document input. While recent models have shown impressive capabilities…
LatentBreak: Jailbreaking Large Language Models through Latent Space Feedback
Raffaele Mura, Giorgio Piras, Kamilė Lukošiūtė +3
Jailbreaks are adversarial attacks designed to bypass the built-in safety mechanisms of large language models. Automated jailbreaks typically optimize an adversarial suffix or adap…
S2AP: Score-space Sharpness Minimization for Adversarial Pruning
Giorgio Piras, Qi Zhao, Fabio Brau +3
Adversarial pruning methods have emerged as a powerful tool for compressing neural networks while preserving robustness against adversarial attacks. These methods typically follow…
Evaluating Line-level Localization Ability of Learning-based Code Vulnerability Detection Models
Marco Pintore, Giorgio Piras, Angelo Sotgiu +2
To address the extremely concerning problem of software vulnerability, system security is often entrusted to Machine Learning (ML) algorithms. Despite their now established detecti…
Prototype-Guided Robust Learning against Backdoor Attacks
Wei Guo, Maura Pintor, Ambra Demontis +1
Backdoor attacks poison the training data, causing the model to behave normally on clean inputs but predict attacker-chosen labels when trigger patterns are embedded into the input…
Silent Until Sparse: Backdoor Attacks on Semi-Structured Sparsity
Wei Guo, Fabio Brau, Maura Pintor +2
Semi-structured (2:4) sparsity is a widely adopted pruning method in modern hardware and software ecosystems (e.g., NVIDIA Sparse Tensor Cores and PyTorch), achieving up to 2X fast…
Evaluating the Evaluators: Trust in Adversarial Robustness Tests
Antonio Emanuele Cinà, Maura Pintor, Luca Demetrio +3
Despite significant progress in designing powerful adversarial evasion attacks for robustness verification, the evaluation of these methods often remains inconsistent and unreliabl…
Regression-aware Continual Learning for Android Malware Detection
Daniele Ghiani, Daniele Angioni, Giorgio Piras +6
Malware evolves rapidly, forcing machine learning-based detectors to be continuously updated. With antivirus vendors processing hundreds of thousands of new samples daily, datasets…
RAID: A Dataset for Testing the Adversarial Robustness of AI-Generated Image Detectors
Hicham Eddoubi, Jonas Ricker, Federico Cocchi +7
AI-generated images have reached a quality level at which humans are incapable of reliably distinguishing them from real images. To counteract the inherent risk of fraud and disinf…
Buffer-free Class-Incremental Learning with Out-of-Distribution Detection
Srishti Gupta, Daniele Angioni, Maura Pintor +4
Class-incremental learning (CIL) poses significant challenges in open-world scenarios, where models must not only learn new classes over time without forgetting previous ones but a…
Adversarial Pruning: A Survey and Benchmark of Pruning Methods for Adversarial Robustness
Giorgio Piras, Maura Pintor, Ambra Demontis +3
Recent work has proposed neural network pruning techniques to reduce the size of a network while preserving robustness against adversarial examples, i.e., well-crafted inputs induc…
HO-FMN: Hyperparameter Optimization for Fast Minimum-Norm Attacks
Raffaele Mura, Giuseppe Floris, Luca Scionis +6
Gradient-based attacks are a primary tool to evaluate robustness of machine-learning models. However, many attacks tend to provide overly-optimistic evaluations as they use fixed l…
Over-parameterization and Adversarial Robustness in Neural Networks: An Overview and Empirical Analysis
Srishti Gupta, Zhang Chen, Luca Demetrio +9
Thanks to their extensive capacity, over-parameterized neural networks exhibit superior predictive capabilities and generalization. However, having a large parameter space is consi…
AttackBench: Evaluating Gradient-based Attacks for Adversarial Examples
Antonio Emanuele Cinà, Jérôme Rony, Maura Pintor +5
Adversarial examples are typically optimized with gradient-based attacks. While novel attacks are continuously proposed, each is shown to outperform its predecessors using differen…
Robustness-Congruent Adversarial Training for Secure Machine Learning Model Updates
Daniele Angioni, Luca Demetrio, Maura Pintor +4
Machine-learning models demand periodic updates to improve their average accuracy, exploiting novel architectures and additional data. However, a newly updated model may commit mis…
-zero: Gradient-based Optimization of -norm Adversarial Examples
Antonio Emanuele Cinà, Francesco Villani, Maura Pintor +3
Evaluating the adversarial robustness of deep networks to gradient-based attacks is challenging. While most attacks consider - and -norm constraints to craft i…
Raze to the Ground: Query-Efficient Adversarial HTML Attacks on Machine-Learning Phishing Webpage Detectors
Biagio Montaruli, Luca Demetrio, Maura Pintor +3
Machine-learning phishing webpage detectors (ML-PWD) have been shown to suffer from adversarial manipulations of the HTML code of the input webpage. Nevertheless, the attacks recen…